Production AI Systems: sections and modules
T4.4
Security, tenancy and prompt injection
Build a threat model for an AI system.
About 4 h 5 min: 35 min reading + 3 h 30 min practice · 6 lessons
- Scope
- Security and multi-tenancy
- Prerequisites
Lessons
Start module- 4
Also used in this module
Lessons taught in another module that this one builds on.
- Secure Multi-Tenant AI Platform
1 h 14 min · Opens the practice page
- The Model Context Protocol
5 min · Credited source
Practise and Check
- Deliverable
- Threat model for P2
- Assessment
- Checkpoint
- Interview probe
- How do you stop prompt injection?
- Common mistakes
- Trusting retrieved text
Your Progress
Saved in this browser when you leave the box.